SAT-CTS delivers the first finite-time regret bounds for combinatorial semi-bandits with satisficing objectives, bounding satisficing regret by a constant when the threshold is realizable and yielding O((log T)^2) standard regret otherwise.
A behavioral model of rational choice
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Bounded-rational agents on networks reach higher stationary coordination probability when connectivity is uniform, with the probability increasing in rationality parameter beta and the partition function approximable by a Gaussian moment-generating function to show regular networks are optimal.
An agent-based model couples individual attention allocation to a depletable global trust stock, producing four distinct regimes where trust level and network fragmentation respond to separate parameter families.
citing papers explorer
-
Multi-User mmWave Beam and Rate Adaptation via Combinatorial Satisficing Bandits
SAT-CTS delivers the first finite-time regret bounds for combinatorial semi-bandits with satisficing objectives, bounding satisficing regret by a constant when the threshold is realizable and yielding O((log T)^2) standard regret otherwise.
-
Learning to Coordinate over Networks with Bounded Rationality
Bounded-rational agents on networks reach higher stationary coordination probability when connectivity is uniform, with the probability increasing in rationality parameter beta and the partition function approximable by a Gaussian moment-generating function to show regular networks are optimal.
-
Modeling Misinformation as a Commons Problem
An agent-based model couples individual attention allocation to a depletable global trust stock, producing four distinct regimes where trust level and network fragmentation respond to separate parameter families.